INDEX

Explanations

punctuation and structure within the text to identify the organization of ideas

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.54

 тоже

-0.52

 IIRC

-0.51

厉害

-0.49

bitur

-0.48

 кстати

-0.46

Anyway

-0.46

来讲

-0.45

 iirc

-0.45

来说

-0.44

POSITIVE LOGITS

 whether

1.28

whether

1.19

无论是

1.16

 regardless

1.15

 either

1.06

either

1.04

regardless

1.04

 especially

1.03

 Whether

1.00

 WHETHER

0.99

Activations Density 0.348%

punctuation and structure within the text to identify the organization of ideas

No Comments

No Known Activations